Merge tag 'noinstr-lds-2020-05-19' into core/rcu

Get the noinstr section and annotation markers to base the RCU parts on.

12 files changed, 137 insertions, 47 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c81b4f3a7268..efc5b83acd2d 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -21,7 +21,7 @@ struct backing_dev_info noop_backing_dev_info = {
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
-const char *bdi_unknown_name = "(unknown)";
+static const char *bdi_unknown_name = "(unknown)";
 
 /*
  * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU
@@ -938,7 +938,8 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
 	if (bdi->dev)	/* The driver needs to use separate queues per device */
 		return 0;
 
-	dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args);
+	vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args);
+	dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name);
 	if (IS_ERR(dev))
 		return PTR_ERR(dev);
 
@@ -1043,6 +1044,14 @@ void bdi_put(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_put);
 
+const char *bdi_dev_name(struct backing_dev_info *bdi)
+{
+	if (!bdi || !bdi->dev)
+		return bdi_unknown_name;
+	return bdi->dev_name;
+}
+EXPORT_SYMBOL_GPL(bdi_dev_name);
+
 static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
diff --git a/mm/gup.c b/mm/gup.c
index 6076df8e04a4..50681f0286de 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1088,7 +1088,7 @@ retry:
 		 * potentially allocating memory.
 		 */
 		if (fatal_signal_pending(current)) {
-			ret = -ERESTARTSYS;
+			ret = -EINTR;
 			goto out;
 		}
 		cond_resched();
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index cd459155d28a..bcabbe02192b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5365,8 +5365,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
+	pud_t *pud, pud_entry;
+	pmd_t *pmd, pmd_entry;
 
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_present(*pgd))
@@ -5376,17 +5376,19 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
-	if (sz != PUD_SIZE && pud_none(*pud))
+	pud_entry = READ_ONCE(*pud);
+	if (sz != PUD_SIZE && pud_none(pud_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pud_huge(*pud) || !pud_present(*pud))
+	if (pud_huge(pud_entry) || !pud_present(pud_entry))
 		return (pte_t *)pud;
 
 	pmd = pmd_offset(pud, addr);
-	if (sz != PMD_SIZE && pmd_none(*pmd))
+	pmd_entry = READ_ONCE(*pmd);
+	if (sz != PMD_SIZE && pmd_none(pmd_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pmd_huge(*pmd) || !pmd_present(*pmd))
+	if (pmd_huge(pmd_entry) || !pmd_present(pmd_entry))
 		return (pte_t *)pmd;
 
 	return NULL;
diff --git a/mm/ksm.c b/mm/ksm.c
index a558da9e7177..281c00129a2e 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2112,8 +2112,16 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 
 		down_read(&mm->mmap_sem);
 		vma = find_mergeable_vma(mm, rmap_item->address);
-		err = try_to_merge_one_page(vma, page,
-					    ZERO_PAGE(rmap_item->address));
+		if (vma) {
+			err = try_to_merge_one_page(vma, page,
+					ZERO_PAGE(rmap_item->address));
+		} else {
+			/*
+			 * If the vma is out of date, we do not need to
+			 * continue.
+			 */
+			err = 0;
+		}
 		up_read(&mm->mmap_sem);
 		/*
 		 * In case of failure, the page was not really empty, so we
diff --git a/mm/madvise.c b/mm/madvise.c
index 4bb30ed6c8d2..8cbd8c1bfe15 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -27,6 +27,7 @@
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 #include <linux/mmu_notifier.h>
+#include <linux/sched/mm.h>
 
 #include <asm/tlb.h>
 
@@ -1090,6 +1091,23 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 	if (write) {
 		if (down_write_killable(&current->mm->mmap_sem))
 			return -EINTR;
+
+		/*
+		 * We may have stolen the mm from another process
+		 * that is undergoing core dumping.
+		 *
+		 * Right now that's io_ring, in the future it may
+		 * be remote process management and not "current"
+		 * at all.
+		 *
+		 * We need to fix core dumping to not do this,
+		 * but for now we have the mmget_still_valid()
+		 * model.
+		 */
+		if (!mmget_still_valid(current->mm)) {
+			up_write(&current->mm->mmap_sem);
+			return -EINTR;
+		}
 	} else {
 		down_read(&current->mm->mmap_sem);
 	}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5beea03dd58a..a3b97f103966 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4990,19 +4990,22 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	unsigned int size;
 	int node;
 	int __maybe_unused i;
+	long error = -ENOMEM;
 
 	size = sizeof(struct mem_cgroup);
 	size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);
 
 	memcg = kzalloc(size, GFP_KERNEL);
 	if (!memcg)
-		return NULL;
+		return ERR_PTR(error);
 
 	memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
 				 1, MEM_CGROUP_ID_MAX,
 				 GFP_KERNEL);
-	if (memcg->id.id < 0)
+	if (memcg->id.id < 0) {
+		error = memcg->id.id;
 		goto fail;
+	}
 
 	memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu);
 	if (!memcg->vmstats_local)
@@ -5046,7 +5049,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 fail:
 	mem_cgroup_id_remove(memcg);
 	__mem_cgroup_free(memcg);
-	return NULL;
+	return ERR_PTR(error);
 }
 
 static struct cgroup_subsys_state * __ref
@@ -5057,8 +5060,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	long error = -ENOMEM;
 
 	memcg = mem_cgroup_alloc();
-	if (!memcg)
-		return ERR_PTR(error);
+	if (IS_ERR(memcg))
+		return ERR_CAST(memcg);
 
 	WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX);
 	memcg->soft_limit = PAGE_COUNTER_MAX;
@@ -5108,7 +5111,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 fail:
 	mem_cgroup_id_remove(memcg);
 	mem_cgroup_free(memcg);
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(error);
 }
 
 static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 69827d4fa052..13cc653122b7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1607,6 +1607,7 @@ void set_zone_contiguous(struct zone *zone)
 		if (!__pageblock_pfn_to_page(block_start_pfn,
 					     block_end_pfn, zone))
 			return;
+		cond_resched();
 	}
 
 	/* We confirm that there is no hole */
@@ -2400,6 +2401,14 @@ static inline void boost_watermark(struct zone *zone)
 
 	if (!watermark_boost_factor)
 		return;
+	/*
+	 * Don't bother in zones that are unlikely to produce results.
+	 * On small machines, including kdump capture kernels running
+	 * in a small area, boosting the watermark can cause an out of
+	 * memory situation immediately.
+	 */
+	if ((pageblock_nr_pages * 4) > zone_managed_pages(zone))
+		return;
 
 	max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
 			watermark_boost_factor, 10000);
diff --git a/mm/percpu.c b/mm/percpu.c
index d7e3bc649f4e..7da7d7737dab 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -80,6 +80,7 @@
 #include <linux/workqueue.h>
 #include <linux/kmemleak.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -1557,10 +1558,9 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 				 gfp_t gfp)
 {
-	/* whitelisted flags that can be passed to the backing allocators */
-	gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
-	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
-	bool do_warn = !(gfp & __GFP_NOWARN);
+	gfp_t pcpu_gfp;
+	bool is_atomic;
+	bool do_warn;
 	static int warn_limit = 10;
 	struct pcpu_chunk *chunk, *next;
 	const char *err;
@@ -1569,6 +1569,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 	void __percpu *ptr;
 	size_t bits, bit_align;
 
+	gfp = current_gfp_context(gfp);
+	/* whitelisted flags that can be passed to the backing allocators */
+	pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
+	is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
+	do_warn = !(gfp & __GFP_NOWARN);
+
 	/*
 	 * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE,
 	 * therefore alignment must be a minimum of that many bytes.
diff --git a/mm/shmem.c b/mm/shmem.c
index d722eb830317..bd8840082c94 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -952,7 +952,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 				VM_BUG_ON_PAGE(PageWriteback(page), page);
 				if (shmem_punch_compound(page, start, end))
 					truncate_inode_page(mapping, page);
-				else {
+				else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
 					/* Wipe the page and don't get stuck */
 					clear_highpage(page);
 					flush_dcache_page(page);
@@ -2179,7 +2179,11 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	int retval = -ENOMEM;
 
-	spin_lock_irq(&info->lock);
+	/*
+	 * What serializes the accesses to info->flags?
+	 * ipc_lock_object() when called from shmctl_do_lock(),
+	 * no serialization needed when called from shm_destroy().
+	 */
 	if (lock && !(info->flags & VM_LOCKED)) {
 		if (!user_shm_lock(inode->i_size, user))
 			goto out_nomem;
@@ -2194,7 +2198,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	retval = 0;
 
 out_nomem:
-	spin_unlock_irq(&info->lock);
 	return retval;
 }
 
@@ -2399,11 +2402,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 
 	lru_cache_add_anon(page);
 
-	spin_lock(&info->lock);
+	spin_lock_irq(&info->lock);
 	info->alloced++;
 	inode->i_blocks += BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
-	spin_unlock(&info->lock);
+	spin_unlock_irq(&info->lock);
 
 	inc_mm_counter(dst_mm, mm_counter_file(page));
 	page_add_file_rmap(page, false);
diff --git a/mm/slub.c b/mm/slub.c
index 332d4b459a90..b762450fc9f0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -551,15 +551,32 @@ static void print_section(char *level, char *text, u8 *addr,
 	metadata_access_disable();
 }
 
+/*
+ * See comment in calculate_sizes().
+ */
+static inline bool freeptr_outside_object(struct kmem_cache *s)
+{
+	return s->offset >= s->inuse;
+}
+
+/*
+ * Return offset of the end of info block which is inuse + free pointer if
+ * not overlapping with object.
+ */
+static inline unsigned int get_info_end(struct kmem_cache *s)
+{
+	if (freeptr_outside_object(s))
+		return s->inuse + sizeof(void *);
+	else
+		return s->inuse;
+}
+
 static struct track *get_track(struct kmem_cache *s, void *object,
 	enum track_item alloc)
 {
 	struct track *p;
 
-	if (s->offset)
-		p = object + s->offset + sizeof(void *);
-	else
-		p = object + s->inuse;
+	p = object + get_info_end(s);
 
 	return p + alloc;
 }
@@ -686,10 +703,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 		print_section(KERN_ERR, "Redzone ", p + s->object_size,
 			s->inuse - s->object_size);
 
-	if (s->offset)
-		off = s->offset + sizeof(void *);
-	else
-		off = s->inuse;
+	off = get_info_end(s);
 
 	if (s->flags & SLAB_STORE_USER)
 		off += 2 * sizeof(struct track);
@@ -782,7 +796,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
  * object address
  * 	Bytes of the object to be managed.
  * 	If the freepointer may overlay the object then the free
- * 	pointer is the first word of the object.
+ *	pointer is at the middle of the object.
  *
  * 	Poisoning uses 0x6b (POISON_FREE) and the last byte is
  * 	0xa5 (POISON_END)
@@ -816,11 +830,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
 
 static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p)
 {
-	unsigned long off = s->inuse;	/* The end of info */
-
-	if (s->offset)
-		/* Freepointer is placed after the object. */
-		off += sizeof(void *);
+	unsigned long off = get_info_end(s);	/* The end of info */
 
 	if (s->flags & SLAB_STORE_USER)
 		/* We also have user information there */
@@ -907,7 +917,7 @@ static int check_object(struct kmem_cache *s, struct page *page,
 		check_pad_bytes(s, page, p);
 	}
 
-	if (!s->offset && val == SLUB_RED_ACTIVE)
+	if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE)
 		/*
 		 * Object and freepointer overlap. Cannot check
 		 * freepointer while object is allocated.
@@ -3533,6 +3543,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 {
 	slab_flags_t flags = s->flags;
 	unsigned int size = s->object_size;
+	unsigned int freepointer_area;
 	unsigned int order;
 
 	/*
@@ -3541,6 +3552,13 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 	 * the possible location of the free pointer.
 	 */
 	size = ALIGN(size, sizeof(void *));
+	/*
+	 * This is the area of the object where a freepointer can be
+	 * safely written. If redzoning adds more to the inuse size, we
+	 * can't use that portion for writing the freepointer, so
+	 * s->offset must be limited within this for the general case.
+	 */
+	freepointer_area = size;
 
 #ifdef CONFIG_SLUB_DEBUG
 	/*
@@ -3579,16 +3597,21 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 		 *
 		 * This is the case if we do RCU, have a constructor or
 		 * destructor or are poisoning the objects.
+		 *
+		 * The assumption that s->offset >= s->inuse means free
+		 * pointer is outside of the object is used in the
+		 * freeptr_outside_object() function. If that is no
+		 * longer true, the function needs to be modified.
 		 */
 		s->offset = size;
 		size += sizeof(void *);
-	} else if (size > sizeof(void *)) {
+	} else if (freepointer_area > sizeof(void *)) {
 		/*
 		 * Store freelist pointer near middle of object to keep
 		 * it away from the edges of the object to avoid small
 		 * sized over/underflows from neighboring allocations.
 		 */
-		s->offset = ALIGN(size / 2, sizeof(void *));
+		s->offset = ALIGN(freepointer_area / 2, sizeof(void *));
 	}
 
 #ifdef CONFIG_SLUB_DEBUG
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 399f219544f7..9a8227afa073 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -34,6 +34,7 @@
 #include <linux/llist.h>
 #include <linux/bitops.h>
 #include <linux/rbtree_augmented.h>
+#include <linux/overflow.h>
 
 #include <linux/uaccess.h>
 #include <asm/tlbflush.h>
@@ -3054,6 +3055,7 @@ finished:
  * @vma:		vma to cover
  * @uaddr:		target user address to start at
  * @kaddr:		virtual address of vmalloc kernel memory
+ * @pgoff:		offset from @kaddr to start at
  * @size:		size of map area
  *
  * Returns:	0 for success, -Exxx on failure
@@ -3066,9 +3068,15 @@ finished:
  * Similar to remap_pfn_range() (see mm/memory.c)
  */
 int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
-				void *kaddr, unsigned long size)
+				void *kaddr, unsigned long pgoff,
+				unsigned long size)
 {
 	struct vm_struct *area;
+	unsigned long off;
+	unsigned long end_index;
+
+	if (check_shl_overflow(pgoff, PAGE_SHIFT, &off))
+		return -EINVAL;
 
 	size = PAGE_ALIGN(size);
 
@@ -3082,8 +3090,10 @@ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
 	if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT)))
 		return -EINVAL;
 
-	if (kaddr + size > area->addr + get_vm_area_size(area))
+	if (check_add_overflow(size, off, &end_index) ||
+	    end_index > get_vm_area_size(area))
 		return -EINVAL;
+	kaddr += off;
 
 	do {
 		struct page *page = vmalloc_to_page(kaddr);
@@ -3122,7 +3132,7 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 						unsigned long pgoff)
 {
 	return remap_vmalloc_range_partial(vma, vma->vm_start,
-					   addr + (pgoff << PAGE_SHIFT),
+					   addr, pgoff,
 					   vma->vm_end - vma->vm_start);
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b06868fc4926..a37c87b5aee2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1625,7 +1625,6 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
  * @dst:	The temp list to put pages on to.
  * @nr_scanned:	The number of pages that were scanned.
  * @sc:		The scan_control struct for this reclaim session
- * @mode:	One of the LRU isolation modes
  * @lru:	LRU list id for isolating
  *
  * returns how many pages were moved onto *@dst.